On the Security of Speech-based Machine Translation Systems: Vulnerabilities and Attacks

In the light of rapid advancement of global connectivity and the increasing reliance onmultilingual communication, speech-based Machine Translation (MT) systems have emerged as essential technologies for facilitating seamless cross-lingual interaction. These systems enable individuals and organizations to overcome linguistic boundaries by automatically translating spoken language in real time. However, despite their growing ubiquity in var- ious applications such as virtual assistants, international conferencing, and accessibility services, the security and robustness of speech-based MT systems remain underexplored. In particular, limited attention has been given to understanding their vulnerabilities under ad- versarial conditions, where malicious actors intentionally craft or manipulate speech inputs to mislead or degrade translation performance. This thesis presents a comprehensive investigation into the security landscape of speech- based machine translation systems from an adversarial perspective. We systematically cat- egorize and analyze potential attack vectors, evaluate their success rates across diverse system architectures and environmental settings, and explore the practical implications of such attacks. Furthermore, through a series of controlled experiments and human-subject evaluations, we demonstrate that adversarial manipulations can significantly distort transla- tion outputs in realistic use cases, thereby posing tangible risks to communication reliability and user trust. Our findings reveal critical weaknesses in current MT models and underscore the ur- gent need for developing more resilient defense strategies. We also discuss open research challenges and propose directions for building secure, trustworthy, and ethically responsible speech translation technologies. Ultimately, this work contributes to a deeper understand- ing of adversarial robustness in multimodal language systems and provides a foundation for advancing the security of next-generation machine translation frameworks.

Name thesis:degree_name

M.S.

Discipline thesis:degree_discipline

Electrical Engineering & Computer Science

Grantor dc:publisher

University of Kansas

Year dc:date.issued

2025

Author dc:creator

• Zhao, Junyi

Advisor dc:contributor.advisor

• Luo, Bo

• Cybersecurity
• Machine Translation
• Natural Language Processing

Language dc:language.iso

en

Dc Identifier Other

https://www.proquest.com/LegacyDocView/DISSNUM/32398587

OAI identifier oai:identifier

oai:kuscholarworks.ku.edu:1808/37716